def main(argv=sys.argv[1:]):
"""Command-line program
Parameters
----------
argv : list, optional
A list of command-line arguments, which will be processed
as if the script were called from the command line if
:func:`main` is called directly.
Default: `sys.argv[1:]`. The command-line arguments, if the script is
invoked from the command line
"""
ap = AnnotationParser()
annotation_file_parser = ap.get_parser(conflict_handler="resolve")
al = AlignmentParser(disabled=_DISABLED)
alignment_file_parser = al.get_parser(conflict_handler="resolve")
mp = MaskParser()
mask_file_parser = mp.get_parser()
bp = BaseParser()
base_parser = bp.get_parser()
parser = argparse.ArgumentParser(description=format_module_docstring(__doc__),
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[base_parser,
alignment_file_parser,
annotation_file_parser,
mask_file_parser],
)
parser.add_argument("outfile",type=str,help="Output filename")
args = parser.parse_args(argv)
bp.get_base_ops_from_args(args)
ga = al.get_genome_array_from_args(args,printer=printer)
transcripts = ap.get_transcripts_from_args(args,printer=printer,return_type=SegmentChain)
crossmap = mp.get_genome_hash_from_args(args,printer=printer)
ga_sum = ga.sum()
normconst = 1000.0*1e6 / ga_sum
with argsopener(args.outfile,args,"w") as fout:
fout.write("## total_dataset_counts: %s\n" % ga_sum)
fout.write("region_name\tregion\tcounts\tcounts_per_nucleotide\trpkm\tlength\n")
for n,ivc in enumerate(transcripts):
name = ivc.get_name()
masks = crossmap.get_overlapping_features(ivc)
ivc.add_masks(*itertools.chain.from_iterable((X for X in masks)))
if n % 1000 == 0:
printer.write("Processed %s regions..." % n)
counts = numpy.nansum(ivc.get_masked_counts(ga))
length = ivc.masked_length
rpnt = numpy.nan if length == 0 else float(counts)/length
rpkm = numpy.nan if length == 0 else rpnt * normconst
ltmp = [name,
str(ivc),
"%.8e" % counts,
"%.8e" % rpnt,
"%.8e" % rpkm,
"%d" % length]
fout.write("%s\n" % "\t".join(ltmp))
fout.close()
printer.write("Processed %s regions total." % n)
printer.write("Done.")
def main(args=sys.argv[1:]):
"""Command-line program
Parameters
----------
argv : list, optional
A list of command-line arguments, which will be processed
as if the script were called from the command line if
:func:`main` is called directly.
Default: `sys.argv[1:]`. The command-line arguments, if the script is
invoked from the command line
"""
al = AlignmentParser()
an = AnnotationParser()
mp = MaskParser()
bp = BaseParser()
alignment_file_parser = al.get_parser(conflict_handler="resolve")
annotation_file_parser = an.get_parser(conflict_handler="resolve")
mask_file_parser = mp.get_parser()
base_parser = bp.get_parser()
parser = argparse.ArgumentParser(
description=format_module_docstring(__doc__),
formatter_class=argparse.RawDescriptionHelpFormatter,
conflict_handler="resolve",
parents=[base_parser, alignment_file_parser, annotation_file_parser, mask_file_parser],
)
parser.add_argument("out_folder", type=str, help="Folder in which to save output vectors")
parser.add_argument(
"--out_prefix", default="", type=str, help="Prefix to prepend to output files (default: no prefix)"
)
parser.add_argument(
"--format", default="%.8f", type=str, help=r"printf-style format string for output (default: '%%.8f')"
)
args = parser.parse_args(args)
bp.get_base_ops_from_args(args)
# if output folder doesn't exist, create it
if not os.path.isdir(args.out_folder):
os.mkdir(args.out_folder)
# parse args
ga = al.get_genome_array_from_args(args, printer=printer)
transcripts = an.get_segmentchains_from_args(args, printer=printer)
mask_hash = mp.get_genome_hash_from_args(args, printer=printer)
# evaluate
for n, tx in enumerate(transcripts):
if n % 1000 == 0:
printer.write("Processed %s regions of interest" % n)
filename = "%s%s.txt" % (args.out_prefix, tx.get_name())
full_filename = os.path.join(args.out_folder, filename)
# mask out overlapping masked regions
overlapping = mask_hash.get_overlapping_features(tx)
for feature in overlapping:
tx.add_masks(*feature.segments)
count_vec = tx.get_masked_counts(ga)
numpy.savetxt(full_filename, count_vec, fmt=args.format)
def main(argv=sys.argv[1:]):
"""Command-line program
Parameters
----------
argv : list, optional
A list of command-line arguments, which will be processed
as if the script were called from the command line if
:py:func:`main` is called directly.
Default: `sys.argv[1:]`. The command-line arguments, if the script is
invoked from the command line
"""
sp = SequenceParser()
mp = MaskParser()
bp = BaseParser()
parser = argparse.ArgumentParser(description=format_module_docstring(__doc__),
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[bp.get_parser(),sp.get_parser(),mp.get_parser()],
)
parser.add_argument("--maxslide",type=int,default=10,
help="Maximum number of nt to search 5\' and 3\' of intron"+
" boundaries (Default: 10)")
parser.add_argument("--ref",type=str,metavar="ref.bed",default=None,
help="Reference file describing known splice junctions")
parser.add_argument("--slide_canonical",action="store_true",default=False,
help="Slide junctions to canonical junctions if present within equal support region")
parser.add_argument("infile",type=str,metavar="input.bed",
help="BED file describing discovered junctions")
parser.add_argument("outbase",type=str,
help="Basename for output files")
args = parser.parse_args(argv)
bp.get_base_ops_from_args(args)
printer.write("Opening genome from %s..." % args.sequence_file)
genome = sp.get_seqdict_from_args(args)
# load crossmap
cross_hash = mp.get_genome_hash_from_args(args)
# load ref junctions
if args.ref is not None:
printer.write("Loading reference junctions from %s" % args.ref)
known_hash = GenomeHash(list(BED_Reader(open(args.ref))),do_copy=False)
else:
known_hash = GenomeHash()
# set up variables
canonicals_plus = [("GT","AG"),
("GC","AG")
]
canonicals_minus = [("CT","AC"),
("CT","GC")
]
known_in_range = 0
canonical_in_range = 0
repetitive = 0
untouched = 0
c = 0
seen_already = []
outfiles = {
"repetitive" : "%s_repetitive.bed" % args.outbase,
"known" : "%s_shifted_known.bed" % args.outbase,
"canonical" : "%s_shifted_canonical.bed" % args.outbase,
"untouched" : "%s_untouched.bed" % args.outbase,
}
outfiles = { K : argsopener(V,args,"w") for K,V in outfiles.items() }
# process data
printer.write("Opening junctions from %s..." % args.infile)
for ivc in BED_Reader(CommentReader(opener(args.infile))):
processed = False
tup = None
if c % 1000 == 0 and c > 0:
printer.write("Processed: %s\tknown: %s\tshifted to canonical: %s\trepetitive: %s\tuntouched: %s" % \
(c, known_in_range, canonical_in_range, repetitive, untouched))
assert len(ivc) == 2
strand = ivc.strand
minus_range, plus_range = find_match_range(ivc,genome,args.maxslide)
# see if either end of splice junction +- match_range lands in repetitive areas of genome
if covered_by_repetitive(ivc,minus_range,plus_range,cross_hash):
repetitive += 1
outfiles["repetitive"].write(ivc.as_bed())
processed = True
# see if one or more known junctions in range
if processed == False and args.ref is not None:
# find_known_in_range(query_ivc,minus_range,plus_range,knownjunctions)
known_juncs = find_known_in_range(ivc,minus_range,plus_range,known_hash.get_nearby_features(ivc))
if len(known_juncs) > 0:
known_in_range += 1
for my_known in known_juncs:
tup = get_junction_tuple(my_known)
if tup not in seen_already:
outfiles["known"].write(my_known.as_bed())
seen_already.append(tup)
processed = True
# see if one or more canonical junctions in range
if processed == False and args.slide_canonical == True:
canonicals = canonicals_plus if strand == "+" else canonicals_minus
#find_canonicals_in_range(query_ivc,minus_range,plus_range,genome,canonicals)
canonical_juncs = find_canonicals_in_range(ivc,minus_range,plus_range,genome,canonicals)
if len(canonical_juncs) > 0:
canonical_in_range += 1
for can in canonical_juncs:
tup = get_junction_tuple(can)
if tup not in seen_already:
outfiles["canonical"].write(can.as_bed())
seen_already.append(tup)
processed = True
if processed == False:
outfiles["untouched"].write(ivc.as_bed())
untouched += 1
c += 1
# save output
printer.write("Totals: %s\tknown: %s\tshifted to canonical: %s\trepetitive: %s\tuntouched: %s" % \
(c, known_in_range, canonical_in_range, repetitive, untouched))
for v in outfiles.values():
v.close()
printer.write("Done.")
def main(args=sys.argv[1:]):
"""Command-line program
Parameters
----------
argv : list, optional
A list of command-line arguments, which will be processed
as if the script were called from the command line if
:func:`main` is called directly.
Default: `sys.argv[1:]`. The command-line arguments, if the script is
invoked from the command line
"""
al = AlignmentParser()
an = AnnotationParser()
mp = MaskParser()
bp = BaseParser()
alignment_file_parser = al.get_parser(conflict_handler="resolve")
annotation_file_parser = an.get_parser(conflict_handler="resolve")
mask_file_parser = mp.get_parser()
base_parser = bp.get_parser()
parser = argparse.ArgumentParser(
description=format_module_docstring(__doc__),
formatter_class=argparse.RawDescriptionHelpFormatter,
conflict_handler="resolve",
parents=[
base_parser, alignment_file_parser, annotation_file_parser,
mask_file_parser
])
parser.add_argument("out_folder",
type=str,
help="Folder in which to save output vectors")
parser.add_argument(
"--out_prefix",
default="",
type=str,
help="Prefix to prepend to output files (default: no prefix)")
parser.add_argument(
"--format",
default="%.8f",
type=str,
help=r"printf-style format string for output (default: '%%.8f')")
args = parser.parse_args(args)
bp.get_base_ops_from_args(args)
# if output folder doesn't exist, create it
if not os.path.isdir(args.out_folder):
os.mkdir(args.out_folder)
# parse args
ga = al.get_genome_array_from_args(args, printer=printer)
transcripts = an.get_segmentchains_from_args(args, printer=printer)
mask_hash = mp.get_genome_hash_from_args(args, printer=printer)
# evaluate
for n, tx in enumerate(transcripts):
if n % 1000 == 0:
printer.write("Processed %s regions of interest" % n)
filename = "%s%s.txt" % (args.out_prefix, tx.get_name())
full_filename = os.path.join(args.out_folder, filename)
# mask out overlapping masked regions
overlapping = mask_hash.get_overlapping_features(tx)
for feature in overlapping:
tx.add_masks(*feature.segments)
count_vec = tx.get_masked_counts(ga)
numpy.savetxt(full_filename, count_vec, fmt=args.format)
def main(argv=sys.argv[1:]):
"""Command-line program
Parameters
----------
argv : list, optional
A list of command-line arguments, which will be processed
as if the script were called from the command line if
:func:`main` is called directly.
Default: `sys.argv[1:]`. The command-line arguments, if the script is
invoked from the command line
"""
ap = AnnotationParser()
annotation_file_parser = ap.get_parser(conflict_handler="resolve")
al = AlignmentParser(disabled=_DISABLED)
alignment_file_parser = al.get_parser(conflict_handler="resolve")
mp = MaskParser()
mask_file_parser = mp.get_parser()
bp = BaseParser()
base_parser = bp.get_parser()
parser = argparse.ArgumentParser(
description=format_module_docstring(__doc__),
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[
base_parser, alignment_file_parser, annotation_file_parser,
mask_file_parser
],
)
parser.add_argument("outfile", type=str, help="Output filename")
args = parser.parse_args(argv)
bp.get_base_ops_from_args(args)
ga = al.get_genome_array_from_args(args, printer=printer)
transcripts = ap.get_transcripts_from_args(args,
printer=printer,
return_type=SegmentChain)
crossmap = mp.get_genome_hash_from_args(args, printer=printer)
ga_sum = ga.sum()
normconst = 1000.0 * 1e6 / ga_sum
with argsopener(args.outfile, args, "w") as fout:
fout.write("## total_dataset_counts: %s\n" % ga_sum)
fout.write(
"region_name\tregion\tcounts\tcounts_per_nucleotide\trpkm\tlength\n"
)
for n, ivc in enumerate(transcripts):
name = ivc.get_name()
masks = crossmap.get_overlapping_features(ivc)
ivc.add_masks(*itertools.chain.from_iterable((X for X in masks)))
if n % 1000 == 0:
printer.write("Processed %s regions..." % n)
counts = numpy.nansum(ivc.get_masked_counts(ga))
length = ivc.masked_length
rpnt = numpy.nan if length == 0 else float(counts) / length
rpkm = numpy.nan if length == 0 else rpnt * normconst
ltmp = [
name,
str(ivc),
"%.8e" % counts,
"%.8e" % rpnt,
"%.8e" % rpkm,
"%d" % length
]
fout.write("%s\n" % "\t".join(ltmp))
fout.close()
printer.write("Processed %s regions total." % n)
printer.write("Done.")
